Empowering ME/CFS Patients: A Predictive Model Using Digital Biomarkers and Integrated Care

Read full text Summarise with VIRAT
Authors: Diāna Arāja, Uldis Berķis, Angelika Krumina, Modra Murovska
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Background: Myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) is a complex, multi-systemic disease with a lack of reliable and universally accepted biomarkers for disease progression. Traditional clinical assessments often fail to capture the nuanced and fluctuating nature of ME/CFS, leading to inadequate monitoring and treatment strategies. Our project lzp-2024/1-0343 “Digital monitoring for integrated progression assessment of myalgic encephalomyelitis/chronic fatigue syndrome” addresses this gap by integrating digital markers derived from patient-device-human interfaces with laboratory and clinical data to enhance the assessment of ME/CFS severity and progression. Approach: Our initiative aims to create a comprehensive and replicable model for tracking ME/CFS progression through digital phenotyping. We involve a multi-disciplinary team comprising clinical researchers, patient advocacy groups, digital health specialists, and data scientists. The co-design of our project is heavily influenced by Personal and Public Involvement (PPI), ensuring that patient voices shape the study framework. Participants receive coaching to independently use wearable devices and complete digital interactional ability tests, tailored to capture self-reported severity metrics. Continuous data collection from these digital interfaces is integrated with liquid biomarkers and imaging data, analysed to determine convergent patterns that predict disease progression. This seamless approach emphasizes patient empowerment and self-management while enhancing clinical replicability. Results: Preliminary findings indicate that digital markers show promise in capturing subtle shifts in disease severity, which align with specific laboratory markers and clinical outcomes. Early pilot data suggest a potential for low-cost, real-time monitoring that reduces patient and healthcare system burden. Moreover, integrating patient-driven digital data has demonstrated improved compliance and engagement, highlighting the feasibility and scalability of this approach. Quantitative results are pending full-scale analysis but indicate a tangible link between digital phenotypes and clinical progression metrics. Implications: Our project offers a transformative model for ME/CFS monitoring, emphasizing patient-centred, data-driven methodologies that can be adapted for other chronic conditions. The approach contributes to a more integrated, holistic framework for healthcare, improves navigation in the healthcare system, and supports Sustainable Development Goal 3 (SDG3) for universal health coverage. Future steps include expanding our predictive toolkit and refining algorithms for wider clinical implementation. We encourage attendees to consider integrating digital phenotyping and low-cost monitoring tools to foster sustainable, high-impact patient care strategies.

Fields of Study & Subjects

Fibromyalgia and Chronic Fatigue Syndrome Research Long-Term Effects of COVID-19 Mobile Health and mHealth Applications

Publication details

Journal / source
International Journal of Integrated Care
Volume
26
Issue
S1
Pages
148–148
Publication date
24 March 2026
Language
EN